big-jump

big-jump is a skill for Claude Code, Codex from LysanderPhong/big-jump. It costs 156 tokens per session (3,069 once invoked), scanned A, original, MIT.

A structured way to turn an unclear software idea into a small, working first release, or to expand an existing project in tested pieces. It covers projects such as websites, APIs, command-line tools, data systems, libraries, and apps.

In plain words
What is it for?
Use it to choose a practical build route, define small testable slices, implement what the environment allows, and verify important claims before release.
Why use it?
It reduces the risk of spending time building the wrong thing. It also separates delivering software from proving that people need or will pay for it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md.

Good fit Use it to choose a practical build route, define small testable slices, implement what the environment allows, and verify important claims before release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lysanderphong/big-jump/big-jump
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add LysanderPhong/big-jump --skill big-jump
Clone the repo
git clone --depth 1 https://github.com/LysanderPhong/big-jump

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for big-jump

README.md
[![agentmods](https://agentmods.dev/badge/skills/lysanderphong/big-jump/big-jump/github.svg)](https://agentmods.dev/skills/lysanderphong/big-jump/big-jump)
Your own site
<a href="https://agentmods.dev/skills/lysanderphong/big-jump/big-jump"><img src="https://agentmods.dev/badge/skills/lysanderphong/big-jump/big-jump/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for big-jump

Your own site · 80×15
<a href="https://agentmods.dev/skills/lysanderphong/big-jump/big-jump"><img src="https://agentmods.dev/badge/skills/lysanderphong/big-jump/big-jump.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,069 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00156 $0.03069
Opus 5 $0.00078 $0.01535
Sonnet 5 $0.00031 $0.00614
Haiku 4.5 $0.00016 $0.00307

Measured 8d ago against content hash 12ac9eafbf03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

big-jump scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl` proves an HTTP response, not browser behavior.
SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Big Jump

Turn motivation or an idea into the smallest real product that proves its value. Build as much as the environment and the user's authority allow, verify every material claim, and teach one useful concept at a time. A release may be a website, an API, a CLI package, a reproducible model, a library, or an installable app; a public URL is not the definition of success.

When the goal includes freelancing or income, treat demand and willingness to pay as hypotheses to test, never as promises. Shipping a website proves that software can be delivered; it does not prove that anyone needs it or will pay for it.

Start by routing the work

Inspect capabilities and workspace state before editing. State the selected route in one short line.

Choose an execution mode:

  • Autonomous — shell and required tools are available. Implement and run checks directly.
  • Guided — commands or required interfaces cannot be run. Produce reviewable files or patches plus exact commands, and ask the user to return the output. Read guided-mode.md.

Choose an engagement:

  • Direction finding — the user wants to build but has no concrete problem, first user, or evidence target. Read ideation-and-coaching.md; do not choose a stack, write product code, or deploy yet. Finish with no more than three directions, one recommended default, and the cheapest next validation action, then reroute the chosen direction as a new build or spike.
  • New build — create a small product from an idea.
  • Existing project — extend a repository while following its instructions, architecture, and native checks.
  • Spike — answer a feasibility question with a time-bounded experiment. Label throwaway work and do not quietly promote it to production.

After direction finding is complete, choose one or more project profiles from project-profiles.md: web UI, backend/API, CLI/automation, data/AI, library/SDK, or mobile/desktop. Mixed systems accumulate the relevant boundary checks.

Read the full file on GitHub · 184 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 184 lines · 156 tokens per session scan A 12ac9eafbf03

Subscribe to this mod's changes

big-jump is a skill published in the GitHub repository LysanderPhong/big-jump (2 stars, last pushed 19d ago), licensed MIT. It adds 156 tokens to every session and 3,069 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.